过拟合： 对训练数据效果好，在测试数据上效果不好。
防止过拟合：
- 增加数据集
- 正则化方法
-
dropout：使一些神经元不工作，减少神经元个数
dropout.png
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data", one_hot=True)
#每个批次的大小
batch_size = 50
#计算一共有多少个批次
n_batch = mnist.train.num_examples // batch_size
#定义输入输出
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])
keep_prob = tf.placeholder(tf.float32)
#创建一个简单的神经网络
#第一层
W1 = tf.Variable(tf.truncated_normal([784, 1000], stddev=0.1))
b1 = tf.Variable(tf.zeros([1000]) + 0.1)
L1 = tf.nn.tanh(tf.matmul(x, W1) + b1)
L1_drop = tf.nn.dropout(L1, keep_prob)
#第二层
W2 = tf.Variable(tf.truncated_normal([1000, 1000], stddev=0.1))
b2 = tf.Variable(tf.zeros([1000]) + 0.1)
L2 = tf.nn.tanh(tf.matmul(L1_drop, W2) + b2)
L2_drop = tf.nn.dropout(L2, keep_prob)
#第三层
W3 = tf.Variable(tf.truncated_normal([1000, 500], stddev=0.1))
b3 = tf.Variable(tf.zeros([500]) + 0.1)
L3 = tf.nn.tanh(tf.matmul(L2_drop, W3) + b3)
L3_drop = tf.nn.dropout(L3, keep_prob)
#第三层
W4 = tf.Variable(tf.truncated_normal([500, 10], stddev=0.1))
b4 = tf.Variable(tf.zeros([10]) + 0.1)
predictions_1 = tf.nn.sigmoid(tf.matmul(L3_drop, W4) + b4)
#定义代价函数
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=predictions_1))
#使用梯度下降
train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)
#初始化变量
init = tf.global_variables_initializer()
#结果存放在一个bool型列表中
correction = tf.equal(tf.argmax(y, 1), tf.argmax(predictions_1, 1))#argmax返回一维张量中最大的值所在的位置
#求准确率
accuracy = tf.reduce_mean(tf.cast(correction, tf.float32))
with tf.Session() as sess:
sess.run(init)
for epoch in range(21):
for batch in range(n_batch):
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
sess.run(train_step, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1})
test_acc = sess.run(accuracy, feed_dict={x: mnist.test.images, y: mnist.test.labels, keep_prob: 1})
train_acc = sess.run(accuracy, feed_dict={x: mnist.train.images, y: mnist.train.labels, keep_prob: 1})
a = mnist.test.labels
print("epoch " + str(epoch) + ", test accuracy " + str(test_acc) + ", train accuracy " + str(train_acc))
